site banner

Small-Scale Question Sunday for September 15, 2024

Do you have a dumb question that you're kind of embarrassed to ask in the main thread? Is there something you're just not sure about?

This is your opportunity to ask questions. No question too simple or too silly.

Culture war topics are accepted, and proposals for a better intro post are appreciated.

1
Jump in the discussion.

No email address required.

I'm reading Nate's blog currently, and this review of the book does not terribly surprise me. In general, I get the impression that he has a prodigious ability to silence his own biases when the data goes against them - in my experience a very unusual skill - , combined with a serious attitude to competently do the single thing he is doing. But in most other ways he is not actually very exceptional. His polling/election model, which he is focusing pretty much all his attention on, is well done and very reasonable, but it doesn't actually include anything surprising. It's just that the competition tend to blatantly ignore or diminish the biases of their favourite polls or use kind-of insane assumptions, such as current-538 (which isn't affiliated with Nate in any way, under the hood) enforcing a fundamentals-only polling approach that, among other things, led to a better election forecast when DEMs polled badly.